Ai Content Pipeline

Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merg...

Security Scan

The skill's instructions require installing and logging into a third‑party CLI and call many external services, but the skill metadata declares no install requirements or credentials — this mismatch is concerning and deserves caution before installing.

Purpose & Capability

The declared purpose (orchestration of multi-step AI content pipelines) aligns with the workflow examples, but the metadata lists no required binaries, no install steps, and no credentials while the SKILL.md clearly assumes the infsh CLI is installed and that you will log into the inference.sh platform and call many hosted apps. The lack of declared requirements (especially authentication) is inconsistent with the workflows shown.

Instruction Scope

SKILL.md explicitly instructs running curl -fsSL https://cli.inference.sh | sh, running infsh login, and executing many infsh app run commands that will transmit content to third-party services. These instructions direct the agent (or user) to download and execute code and to send potentially sensitive or proprietary content to external endpoints. The docs also rely on interactive login and implicit saved credentials, none of which are declared in the metadata.

Install Mechanism

Although there is no formal install spec in the registry, the instructions recommend piping a remote installer (cli.inference.sh) to sh and downloading binaries from dist.inference.sh. These are download-and-execute operations from a domain that is not a well-known package host; while checksums are referenced, running arbitrary remote install scripts is a higher-risk install mechanism and should be validated manually.

Credentials

The skill metadata declares no required environment variables or primary credential, but the workflows require running infsh login and will likely need API keys/tokens (for inference.sh and for the many backend apps like openrouter, falai, bytedance, etc.). This omission means the skill does not declare the credentials it will need or store, which is a meaningful mismatch and raises the risk of undocumented credential usage or accidental exposure.

Persistence & Privilege

always:false (good), and the skill is not requesting special platform privileges. However, the install instruction will place a binary on disk and infsh login will typically persist credentials locally; these side effects are not declared by the registry metadata and could create persistent agent-facing credentials/configuration on the host.

What to consider before installing

This skill appears to be an orchestrator that expects you to install and log into the inference.sh CLI and then call many third‑party services. Before installing: (1) do not blindly run curl | sh — download the installer, inspect it, and verify checksums manually; (2) confirm you trust cli.inference.sh / dist.inference.sh and read their privacy/security docs; (3) be prepared that logging in will persist credentials locally and that your content will be sent to external inference providers; (4) avoid supplying high‑privilege or broad tokens — use least privilege and ephemeral keys where possible; (5) if possible, trial the workflow in an isolated/sandboxed environment or VM to limit blast radius; (6) ask the publisher for an explicit list of required credentials and what the CLI stores and transmits. The inconsistencies (no declared install/credentials despite clear install/login steps) make this risky until you validate the external tooling.

Build multi-step content creation pipelines via inference.sh CLI.

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

# Simple pipeline: Generate image -> Animate to video
infsh app run falai/flux-dev --input '{"prompt": "portrait of a woman smiling"}' > image.json
infsh app run falai/wan-2-5 --input '{"image_url": "<url-from-previous>"}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Pipeline Patterns

Pattern 1: Image -> Video -> Audio

[FLUX Image] -> [Wan 2.5 Video] -> [Foley Sound]

Pattern 2: Script -> Speech -> Avatar

[LLM Script] -> [Kokoro TTS] -> [OmniHuman Avatar]

Pattern 3: Research -> Content -> Distribution

[Tavily Search] -> [Claude Summary] -> [FLUX Visual] -> [Twitter Post]

Complete Workflows

YouTube Short Pipeline

Create a complete short-form video from a topic.

# 1. Generate script with Claude
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a 30-second script about the future of AI. Make it engaging and conversational. Just the script, no stage directions."
}' > script.json

# 2. Generate voiceover with Kokoro
infsh app run infsh/kokoro-tts --input '{
  "text": "<script-text>",
  "voice": "af_sarah"
}' > voice.json

# 3. Generate background image with FLUX
infsh app run falai/flux-dev --input '{
  "prompt": "Futuristic city skyline at sunset, cyberpunk aesthetic, 4K wallpaper"
}' > background.json

# 4. Animate image to video with Wan
infsh app run falai/wan-2-5 --input '{
  "image_url": "<background-url>",
  "prompt": "slow camera pan across cityscape, subtle movement"
}' > video.json

# 5. Add captions (manually or with another tool)

# 6. Merge video with audio
infsh app run infsh/media-merger --input '{
  "video_url": "<video-url>",
  "audio_url": "<voice-url>"
}'

Talking Head Video Pipeline

Create an AI avatar presenting content.

# 1. Write the script
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a 1-minute explainer script about quantum computing for beginners."
}' > script.json

# 2. Generate speech
infsh app run infsh/kokoro-tts --input '{
  "text": "<script>",
  "voice": "am_michael"
}' > speech.json

# 3. Generate or use a portrait image
infsh app run falai/flux-dev --input '{
  "prompt": "Professional headshot of a friendly tech presenter, neutral background, looking at camera"
}' > portrait.json

# 4. Create talking head video
infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "<portrait-url>",
  "audio_url": "<speech-url>"
}' > talking_head.json

Product Demo Pipeline

Create a product showcase video.

# 1. Generate product image
infsh app run falai/flux-dev --input '{
  "prompt": "Sleek wireless earbuds on white surface, studio lighting, product photography"
}' > product.json

# 2. Animate product reveal
infsh app run falai/wan-2-5 --input '{
  "image_url": "<product-url>",
  "prompt": "slow 360 rotation, smooth motion"
}' > product_video.json

# 3. Upscale video quality
infsh app run falai/topaz-video-upscaler --input '{
  "video_url": "<product-video-url>"
}' > upscaled.json

# 4. Add background music
infsh app run infsh/media-merger --input '{
  "video_url": "<upscaled-url>",
  "audio_url": "https://your-music.mp3",
  "audio_volume": 0.3
}'

Blog to Video Pipeline

Convert written content to video format.

# 1. Summarize blog post
infsh app run openrouter/claude-haiku-45 --input '{
  "prompt": "Summarize this blog post into 5 key points for a video script: <blog-content>"
}' > summary.json

# 2. Generate images for each point
for i in 1 2 3 4 5; do
  infsh app run falai/flux-dev --input "{
    \"prompt\": \"Visual representing point $i: <point-text>\"
  }" > "image_$i.json"
done

# 3. Animate each image
for i in 1 2 3 4 5; do
  infsh app run falai/wan-2-5 --input "{
    \"image_url\": \"<image-$i-url>\"
  }" > "video_$i.json"
done

# 4. Generate voiceover
infsh app run infsh/kokoro-tts --input '{
  "text": "<full-script>",
  "voice": "bf_emma"
}' > narration.json

# 5. Merge all clips
infsh app run infsh/media-merger --input '{
  "videos": ["<video1>", "<video2>", "<video3>", "<video4>", "<video5>"],
  "audio_url": "<narration-url>",
  "transition": "crossfade"
}'

Pipeline Building Blocks

Content Generation

Step	App	Purpose
Script	openrouter/claude-sonnet-45	Write content
Research	tavily/search-assistant	Gather information
Summary	openrouter/claude-haiku-45	Condense content

Visual Assets

Step	App	Purpose
Image	falai/flux-dev	Generate images
Image	google/imagen-3	Alternative image gen
Upscale	falai/topaz-image-upscaler	Enhance quality

Animation

Step	App	Purpose
I2V	falai/wan-2-5	Animate images
T2V	google/veo-3-1-fast	Generate from text
Avatar	bytedance/omnihuman-1-5	Talking heads

Audio

Step	App	Purpose
TTS	infsh/kokoro-tts	Voice narration
Music	infsh/ai-music	Background music
Foley	infsh/hunyuanvideo-foley	Sound effects

Post-Production

Step	App	Purpose
Upscale	falai/topaz-video-upscaler	Enhance video
Merge	infsh/media-merger	Combine media
Caption	infsh/caption-video	Add subtitles

Best Practices

1. Plan the pipeline first - Map out each step before running
2. Save intermediate results - Store outputs for iteration
3. Use appropriate quality - Fast models for drafts, quality for finals
4. Match resolutions - Keep consistent aspect ratios throughout
5. Test each step - Verify outputs before proceeding

Related Skills

# Video generation models
npx skills add inference-sh/skills@ai-video-generation

# Image generation
npx skills add inference-sh/skills@ai-image-generation

# Text-to-speech
npx skills add inference-sh/skills@text-to-speech

# LLM models for scripts
npx skills add inference-sh/skills@llm-models

# Full platform skill
npx skills add inference-sh/skills@inference-sh

Browse all apps: infsh app list

Documentation

• Content Pipeline Example - Official pipeline guide
• Building Workflows - Workflow best practices